A robust region-based global camera estimation method for video sequences

Author

Xuesong Le ; Gonzalez, R.

Author_Institution

Sch. of ICT, Griffith Univ., Southport, QLD, Australia

fYear

2013

fDate

16-18 Dec. 2013

Firstpage

1

Lastpage

7

Abstract

Global motion estimation (GME) plays an important role in video object segmentation. This paper presents a computationally efficient three stage affine GME algorithm, using radius-based Fourier Descriptors from histogram-based image segmented regions. Then a variance-cut KD tree is used for initial matching between FDs. and an efficient two-step outlier method is applied to remove incorrect outliers. Experiments with different video sequences are used to demonstrate the performance of the proposed approach.

Keywords

affine transforms; cameras; image segmentation; image sequences; motion estimation; computationally efficient three stage affine GME algorithm; global motion estimation; histogram-based image segmented regions; radius-based Fourier descriptors; robust region-based global camera estimation method; two-step outlier method; video object segmentation; video sequences; Computational modeling; Equations; Feature extraction; Image segmentation; Mathematical model; Shape; Vectors; Fourier Descriptors; affine motion estimation; outliers removal;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing and Communication Systems (ICSPCS), 2013 7th International Conference on

Conference_Location

Carrara, VIC

Type

conf

DOI

10.1109/ICSPCS.2013.6723970

Filename

6723970